Commands reference

Slash commands control Claude Code from inside a session. Type / to see everything available, or / followed by letters to filter. Commands marked Skill are bundled skills — prompt-based workflows Claude can also trigger automatically when relevant.

For the official reference see code.claude.com/docs/en/commands.

---

Top 26 commands

Daily use

Commands you’ll reach for in almost every session.

Command	What it does
/clear	Clear conversation history and free up context. Aliases: /reset, /new
/compact [instructions]	Summarize the conversation to reclaim context. Pass instructions to focus what’s kept, e.g. /compact focus on the auth changes
/model [model]	Switch the active model mid-session. Takes effect immediately — no need to restart
/plan [description]	Enter plan mode. Pass a description to jump straight in: /plan fix the auth bug
/cost	Show token usage and session cost. See cost tracking docs
/context	Visualize context window usage as a colored grid with optimization suggestions
/rewind	Rewind the conversation and/or code to a previous point. See checkpointing docs. Alias: /checkpoint
/btw <question>	Ask a quick side question without adding it to the main conversation thread

Session

Manage, navigate, and share your sessions.

Command	What it does
/resume [session]	Resume a previous conversation by name or ID, or open the session picker. Alias: /continue
/rename [name]	Name the current session — shows on the prompt bar. Omit the name to auto-generate one
/branch [name]	Fork the conversation at this point to explore a different direction. Alias: /fork
/copy [N]	Copy the last assistant response to clipboard. /copy 2 copies the second-to-last. Shows a picker when code blocks are present
/export [filename]	Export the current conversation as plain text to a file or clipboard
/diff	Open an interactive diff viewer showing uncommitted changes and per-turn diffs. Use arrows to navigate
/stats	Visualize daily usage, session history, streaks, and model preferences

Configuration

Set up Claude Code the way you work.

Command	What it does
/config	Open the Settings UI to adjust theme, model, output style, and other preferences. Alias: /settings
/permissions	Manage allow, ask, and deny rules for tool permissions interactively. See permissions docs. Alias: /allowed-tools
/memory	Edit CLAUDE.md memory files and manage auto-memory entries. See memory docs
/init	Initialize a project with a CLAUDE.md guide. Set CLAUDE_CODE_NEW_INIT=1 for an interactive flow covering skills, hooks, and personal memory
/statusline	Configure the status line at the bottom of Claude Code. Describe what you want in natural language
/hooks	View hook configurations for tool events
/effort [low|medium|high|max|auto]	Set the model effort level. low–high persist across sessions. max is current-session only (Opus 4.6)
/skills	List all available skills, including bundled and custom ones

Power

Advanced workflows and automation.

Command	What it does
/simplify [focus]	Skill Review recently changed files for code quality issues and fix them. Runs three review agents in parallel. Pass text to narrow focus: /simplify focus on memory efficiency
/batch <instruction>	Skill Orchestrate large-scale parallel changes. Decomposes work into up to 30 units, spawns one agent per unit in isolated git worktrees, and opens PRs. Example: /batch migrate src/ from Solid to React
/security-review	Analyze pending changes on the current branch for security vulnerabilities — injection, auth issues, data exposure, and more
/autofix-pr [prompt]	Spawn a remote session that watches your PR and pushes fixes when CI fails or reviewers leave comments. Requires the gh CLI
/ultraplan <prompt>	Draft a plan in an ultraplan session, review it in your browser, then execute remotely or send back to terminal
/schedule [description]	Create, update, list, or run Cloud scheduled tasks conversationally
/debug [description]	Skill Enable debug logging and troubleshoot issues by reading the session debug log. Optionally describe the issue to focus the analysis

---

Full command reference

All commands included in Claude Code. Availability depends on your platform, plan, and environment — some commands only appear on macOS/Windows, or on Pro/Max plans.

Note

<arg> = required argument · [arg] = optional argument · Commands marked Skill are bundled prompt-based workflows.

Command	Purpose
/add-dir <path>	Add a working directory for file access during the current session
/agents	Manage agent configurations
/autofix-pr [prompt]	Spawn a remote session to auto-fix CI failures and PR review comments on your open PR
/batch <instruction>	Skill. Orchestrate large-scale parallel changes across a codebase in isolated worktrees
/branch [name]	Fork the conversation at this point. Alias: /fork
/btw <question>	Ask a side question without adding it to the conversation thread
/chrome	Configure Claude in Chrome settings
/claude-api	Skill. Load Claude API reference for your project’s language. Also activates automatically when your code imports anthropic or @anthropic-ai/sdk
/clear	Clear conversation history and free up context. Aliases: /reset, /new
/color [color|default]	Set the prompt bar color for the current session: red, blue, green, yellow, purple, orange, pink, cyan
/compact [instructions]	Compact conversation with optional focus instructions
/config	Open the Settings UI. Alias: /settings
/context	Visualize current context usage as a colored grid
/copy [N]	Copy the last (or Nth-latest) assistant response to clipboard
/cost	Show token usage statistics
/debug [description]	Skill. Enable debug logging and troubleshoot the current session
/desktop	Continue the session in the Claude Code Desktop app. macOS and Windows only. Alias: /app
/diff	Open an interactive diff viewer showing uncommitted changes and per-turn diffs
/doctor	Diagnose and verify your Claude Code installation and settings
/effort [level]	Set model effort: low, medium, high, max, or auto
/exit	Exit the CLI. Alias: /quit
/export [filename]	Export the current conversation as plain text
/extra-usage	Configure extra usage to keep working when rate limits are hit
/fast [on|off]	Toggle fast mode
/feedback [report]	Submit feedback about Claude Code. Alias: /bug
/help	Show help and available commands
/hooks	View hook configurations for tool events
/ide	Manage IDE integrations and show status
/init	Initialize project with a CLAUDE.md guide
/insights	Generate a report analyzing your Claude Code sessions and interaction patterns
/install-github-app	Set up the Claude GitHub Actions app for a repository
/install-slack-app	Install the Claude Slack app
/keybindings	Open or create your keybindings configuration file
/login	Sign in to your Anthropic account
/logout	Sign out from your Anthropic account
/loop [interval] [prompt]	Skill. Run a prompt repeatedly while the session stays open. See scheduled tasks
/mcp	Manage MCP server connections and OAuth authentication
/memory	Edit CLAUDE.md memory files and manage auto-memory
/mobile	Show QR code to download the Claude mobile app. Aliases: /ios, /android
/model [model]	Select or change the AI model
/passes	Share a free week of Claude Code with friends (account-eligible only)
/permissions	Manage allow, ask, and deny rules for tool permissions. Alias: /allowed-tools
/plan [description]	Enter plan mode, optionally with an initial task
/plugin	Manage Claude Code plugins
/powerup	Discover Claude Code features through quick interactive lessons
/privacy-settings	View and update privacy settings (Pro and Max plans only)
/release-notes	View the changelog in an interactive version picker
/reload-plugins	Reload all active plugins to apply changes without restarting
/remote-control	Make this session available for remote control from claude.ai. Alias: /rc
/remote-env	Configure the default remote environment for web sessions
/rename [name]	Rename the current session
/resume [session]	Resume a conversation by ID or name. Alias: /continue
/rewind	Rewind conversation and/or code to a previous point. See checkpointing. Alias: /checkpoint
/sandbox	Toggle sandbox mode (supported platforms only)
/schedule [description]	Create, update, list, or run Cloud scheduled tasks
/security-review	Analyze pending changes for security vulnerabilities
/setup-bedrock	Configure Amazon Bedrock authentication and settings (requires CLAUDE_CODE_USE_BEDROCK=1)
/setup-vertex	Configure Google Vertex AI authentication and settings (requires CLAUDE_CODE_USE_VERTEX=1)
/simplify [focus]	Skill. Review and fix recently changed files for code quality issues
/skills	List available skills
/stats	Visualize daily usage, session history, streaks, and model preferences
/status	Open Settings (Status tab) showing version, model, account, and connectivity
/statusline	Configure Claude Code’s status line
/stickers	Order Claude Code stickers
/tasks	List and manage background tasks. Alias: /bashes
/teleport	Pull a Claude Code web session into this terminal. Alias: /tp
/terminal-setup	Configure terminal keybindings for Shift+Enter and other shortcuts
/theme	Change the color theme, including light, dark, colorblind-accessible, and ANSI variants
/ultraplan <prompt>	Draft and execute a plan in an ultraplan session
/upgrade	Open the upgrade page to switch plan tier
/usage	Show plan usage limits and rate limit status
/voice	Toggle push-to-talk voice dictation
/web-setup	Connect your GitHub account to Claude Code on the web

---

Related docs

• Commands reference — official full reference
• Customize your status line — set up a rich statusline with git, model, context, and cost
• Skills — create your own slash commands
• Permissions — control tool and skill access
• Memory & CLAUDE.md — persistent project context
• Hooks — automate workflows around tool events
• Interactive mode — keyboard shortcuts, vim mode, command history
• Checkpointing — rewind and branch conversations
• Subagents — delegate tasks to specialized agents